Al and Multimodal Research: Turning Biological Complexity into Therapeutic Opportunity

Drug discovery is increasingly multimodal, spanning small molecules, antibodies, RNA-based therapies, cell and gene therapies, and novel combinations like ADCs. Each modality generates unique biological questions and massive datasets, creating both opportunity and complexity. Making sense of this data is now central to advancing discovery.

A concrete example comes from the work of Alex Zagajewski and the team at Novo Nordisk Research Centre Oxford, a high-throughput cellular differentiation screening platform was developed on human adipocytes, integrating single-gene knockouts, time-course imaging, and multi-omic analyses. By applying AI/ML and mechanistic modeling, novel regulators of adipogenesis and potential therapeutic targets were identified—demonstrating how computational integration can unlock insights from complex biological data.

What you will learn:

• How multimodal datasets (imaging, transcriptomics, proteomics, etc.) can drive new insights in drug discovery.
• The role of AI/ML in translating large-scale biological complexity into actionable therapeutic hypotheses.
• Case examples of integrating functional genomics and advanced analytics to identify novel targets.
• Why cross-modality data integration is becoming a cornerstone of next-generation discovery pipelines.

Who should attend:

• Scientists and researchers working across small molecule, biologic, RNA, cell, and gene therapy discovery.
• Data scientists and computational biologists applying AI/ML to life sciences.
• R&D leaders and decision-makers seeking strategies to accelerate multimodal drug discovery.
• Translational and functional genomics teams looking to connect data complexity to therapeutic opportunity.